{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0061982830755880625, "eval_steps": 10, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00012396566151176124, "eval_loss": NaN, "eval_runtime": 126.4705, "eval_samples_per_second": 26.86, "eval_steps_per_second": 13.434, "step": 1 }, { "epoch": 0.0006198283075588062, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.0012396566151176124, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.0012396566151176124, "eval_loss": NaN, "eval_runtime": 125.5255, "eval_samples_per_second": 27.062, "eval_steps_per_second": 13.535, "step": 10 }, { "epoch": 0.0018594849226764186, "grad_norm": NaN, "learning_rate": 9.619397662556435e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.002479313230235225, "grad_norm": NaN, "learning_rate": 8.535533905932738e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.002479313230235225, "eval_loss": NaN, "eval_runtime": 125.6988, "eval_samples_per_second": 27.025, "eval_steps_per_second": 13.516, "step": 20 }, { "epoch": 0.0030991415377940312, "grad_norm": NaN, "learning_rate": 6.91341716182545e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.003718969845352837, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.003718969845352837, "eval_loss": NaN, "eval_runtime": 128.4748, "eval_samples_per_second": 26.441, "eval_steps_per_second": 13.224, "step": 30 }, { "epoch": 0.004338798152911644, "grad_norm": NaN, "learning_rate": 3.086582838174551e-05, "loss": 0.0, "step": 35 }, { "epoch": 0.00495862646047045, "grad_norm": NaN, "learning_rate": 1.4644660940672627e-05, "loss": 0.0, "step": 40 }, { "epoch": 0.00495862646047045, "eval_loss": NaN, "eval_runtime": 124.2176, "eval_samples_per_second": 27.347, "eval_steps_per_second": 13.678, "step": 40 }, { "epoch": 0.005578454768029256, "grad_norm": NaN, "learning_rate": 3.8060233744356633e-06, "loss": 0.0, "step": 45 }, { "epoch": 0.0061982830755880625, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 50 }, { "epoch": 0.0061982830755880625, "eval_loss": NaN, "eval_runtime": 124.0062, "eval_samples_per_second": 27.394, "eval_steps_per_second": 13.701, "step": 50 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1848500073529344.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }